Конечные точки REST API для внедрения моделей

Используйте REST API для работы с внедрением запросов на модели.

Run an embedding request attributed to an organization

This endpoint allows you to run an embedding request attributed to a specific organization. You must be a member of the organization and have enabled models to use this endpoint. The token used to authenticate must have the models: read permission if using a fine-grained PAT or GitHub App minted token. The request body should contain the model ID and the input text(s) for the embedding request. The response will include the generated embeddings.

Параметры для "Run an embedding request attributed to an organization"

Заголовки
Имя., Тип, Description
`accept` string Setting to `application/vnd.github+json` is recommended.

Параметры пути
Имя., Тип, Description
`org` string Обязательное поле The organization login associated with the organization to which the request is to be attributed.

Параметры запроса
Имя., Тип, Description
`api-version` string The API version to use. Optional, but required for some features.

Параметры запроса
Имя., Тип, Description
`model` string Обязательное поле ID of the specific model to use for the request. The model ID should be in the format of {publisher}/{model_name} where "openai/text-embedding-3-small" is an example of a model ID. You can find supported models in the catalog/models endpoint.
`input` string or array Обязательное поле Input text to embed, encoded as a string or array of strings. To embed multiple inputs in a single request, pass an array of strings. Each input must not exceed the max input tokens for the model, cannot be an empty string, and any array must be 2048 dimensions or less.
`encoding_format` string The format to return the embeddings in. Can be either float or base64. По умолчанию.: `float` Возможные значения: `float`, `base64`
`dimensions` integer The number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3 and later models.
`user` string A unique identifier representing your end-user, which can help us to monitor and detect abuse.

Коды состояния http-ответа для "Run an embedding request attributed to an organization"

Код состояния	Описание
`200`	OK

Примеры кода для "Run an embedding request attributed to an organization"

Пример запроса

post/orgs/{org}/inference/embeddings

curl -L \
  -X POST \
  -H "Accept: application/vnd.github+json" \
  -H "Authorization: Bearer <YOUR-TOKEN>" \
  -H "X-GitHub-Api-Version: 2022-11-28" \
  https://models.github.ai/orgs/ORG/inference/embeddings \
  -d '{"model":"openai/text-embedding-3-small","input":["The food was delicious and the waiter was very friendly.","I had a great time at the restaurant."]}'

Response

Status: 200

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        0.0023064255,
        -0.009327292,
        -0.0028842222
      ]
    }
  ],
  "model": "openai/text-embedding-3-small",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}

Run an embedding request

This endpoint allows you to run an embedding request. The token used to authenticate must have the models: read permission if using a fine-grained PAT or GitHub App minted token. The request body should contain the model ID and the input text(s) for the embedding request. The response will include the generated embeddings.

Параметры для "Run an embedding request"

Заголовки
Имя., Тип, Description
`accept` string Setting to `application/vnd.github+json` is recommended.

Параметры запроса
Имя., Тип, Description
`api-version` string The API version to use. Optional, but required for some features.

Параметры запроса
Имя., Тип, Description
`model` string Обязательное поле ID of the specific model to use for the request. The model ID should be in the format of {publisher}/{model_name} where "openai/text-embedding-3-small" is an example of a model ID. You can find supported models in the catalog/models endpoint.
`input` string or array Обязательное поле Input text to embed, encoded as a string or array of strings. To embed multiple inputs in a single request, pass an array of strings. Each input must not exceed the max input tokens for the model, cannot be an empty string, and any array must be 2048 dimensions or less.
`encoding_format` string The format to return the embeddings in. Can be either float or base64. По умолчанию.: `float` Возможные значения: `float`, `base64`
`dimensions` integer The number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3 and later models.
`user` string A unique identifier representing your end-user, which can help us to monitor and detect abuse.

Коды состояния http-ответа для "Run an embedding request"

Код состояния	Описание
`200`	OK

Примеры кода для "Run an embedding request"

Пример запроса

post/inference/embeddings

curl -L \
  -X POST \
  -H "Accept: application/vnd.github+json" \
  -H "Authorization: Bearer <YOUR-TOKEN>" \
  -H "X-GitHub-Api-Version: 2022-11-28" \
  https://models.github.ai/inference/embeddings \
  -d '{"model":"openai/text-embedding-3-small","input":["The food was delicious and the waiter was very friendly.","I had a great time at the restaurant."]}'

Response

Status: 200

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        0.0023064255,
        -0.009327292,
        -0.0028842222
      ]
    }
  ],
  "model": "openai/text-embedding-3-small",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}